• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.245-248
• /
• 2000

In this paper we improve the performance of autonomous mobile robot by induction of reinforcement learning concept. Generally, the system used in this paper is divided into two part. Namely, one is neural-fuzzy and the other is dynamic recurrent neural networks. Neural-fuzzy determines the next action of robot. Also, the neural-fuzzy is determined to optimal action internal reinforcement from dynamic recurrent neural network. Dynamic recurrent neural network evaluated to determine action of neural-fuzzy by external reinforcement signal from environment, Besides, dynamic recurrent neural network weight determined to internal reinforcement signal value is evolved by genetic algorithms. The architecture of propose system is applied to the computer simulations on controlling autonomous mobile robot.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.21 no.7
• /
• pp.103-108
• /
• 2007

Neural network is used in many fields of control systems currently. However, It is not easy to obtain input-output pattern when neural network is used for the system of a single feedback controller and it is difficult to get satisfied performance with neural network when load changes rapidly or disturbance is applied. To resolve these problems, this paper proposes a new mode to implement a neural network controller by installing a real object in place of activation function of Neural Network output node. As the Neural Network self adaptive control system is designed in simple structure neural network input-output pattern problem is solved naturally and real tin Loaming becomes possible through general back propagation algorithm. The effect of the proposed Neural Network self adaptive control algorithm was verified in a test of controlling the speed of a A.C. servo motor equipped with a high speed computing capable DSP (TMS320C32) on which the proposed algorithm was loaded.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10b
• /
• pp.326-328
• /
• 2000

인공신경회로망 기술은 선형 또는 비선형성 계산 문제를 복잡도에 무관하게 학습에 의해 자동으로 근사한다. 또한 알고리즘이 단순하며 잡음에 강하여 다양한 분야에 적용되고 있다. 반면 대상시스템의 특성이나 조건이 변경되면 계산성능을 보장할 수 없고, 계산의 신뢰성 보장 한계가 모호하기 때문에 제어문제에는 실용화가 어려운 것으로 알려져 있다. 제안 모델은 인공신경회로망의 장점을 유지하면서, 위와 같은 문제점을 해결한다. 시뮬레이션을 통하여 제안 모델은 기존 제어기에 비해 우수한 추종제어성능을 보이는 것으로 밝혀졌다.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.39 no.2
• /
• pp.157-165
• /
• 2002

This paper presents the implementation of the speed control system for 3 phase induction motor using PD controller and neural networks. The PD controller is used to control the motor and to train neural networks at the first time. And neural networks are widely used as controllers because of a nonlinear mapping capability, we used feedforward neural networks(FNN) in order to simply design the speed control system of the 3 phase induction motor. Neural networks are tuned online using the speed reference, actual speed measured from an encoder and control input current to motor. PD controller and neural networks are applied to the speed control system for 3 phase induction motor, are compared with PI controller through computer simulation and experiment respectively. The results are illustrated that the output of the PD controller is decreased and feedforward neural networks act main controller, and the proposed hybrid controllers show better performance than the PI controller in abrupt load variation and the precise control is possible because the steady state error can be minimized by training neural networks.

• Journal of Radiation Protection and Research
• /
• v.40 no.1
• /
• pp.55-64
• /
• 2015

Dose calculations which are a crucial requirement for radiotherapy treatment planning systems require accuracy and rapid calculations. The conventional radiotherapy treatment planning dose algorithms are rapid but lack precision. Monte Carlo methods are time consuming but the most accurate. The new combined system that Monte Carlo methods calculate part of interesting domain and the rest is calculated by neural can calculate the dose distribution rapidly and accurately. The preliminary study showed that neural networks can map functions which contain discontinuous points and inflection points which the dose distributions in inhomogeneous media also have. Performance results between scaled conjugated gradient algorithm and Levenberg-Marquardt algorithm which are used for training the neural network with a different number of neurons were compared. Finally, the dose distributions of homogeneous phantom calculated by a commercialized treatment planning system were used as training data of the neural network. In the case of homogeneous phantom;the mean squared error of percent depth dose was 0.00214. Further works are programmed to develop the neural network model for 3-dimensinal dose calculations in homogeneous phantoms and inhomogeneous phantoms.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.2
• /
• pp.439-448
• /
• 1999

In this paper, two optimization algorithms based on artificial neural networks and genetic algorithms are proposed for cellular radio channel assignment problems. The channel assignment process is characterized as minimization of the energy function which represents constraints of the channel assignment problems. All three constraints such as the co-channel constraint, the adjacent channel constraint and the co-site channel constraint are considered. In the neural networks approach, certain techniques such as the forced assignment and the changing cell order are developed, and in the genetic algorithms approach, data structure and proper genetic operators are developed to find optimal solutions, As simulation results, the convergence rates of the two approaches are presented and compared.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.18 no.5
• /
• pp.634-642
• /
• 1993

In this paper a new trajectory control method is proposed for a robot manipulator using a time delay neural network(TDNN) as a feedforward controller with an algorithm to learn inverse dynamics of the manipulator. The TDNN structure has so favorable characteristics that neurons can extract more dynamic information from both present and past input signals and perform more efficient learning. The TDNN neural network receives two normalized inputs, one of which is the reference trajectory signal and the other of which is the error signals from the PD controller. It is proved that the normalized inputs to the TDNN neural network can enhance the learning efficiency of the neural network. The proposed scheme was investigated for the planar robot manipulator with two joints by computer simulation.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.15 no.1
• /
• pp.137-146
• /
• 2002

The predictions of the loading characteristics was performed by the neural networks which use the results through structural analysis. The momentum backperpagtion which can be modified the teaming rate and momentum coefficient, was developed. Input patterns of the neural networks are the 9 strains which positioned at the side of the shell and output layers is the loading characteristics. Hidden layers were increased from 1 layers to 3 layers. Developed program which were trained by 9 strains predict the loading characteristics under 0.5%. Inverse engineering can be applicable to the composite laminated cylindrical shells with developed neural networks.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.6
• /
• pp.1135-1141
• /
• 2004

In this study, this system makes use of the analog infrared rays sensor and converts the feature of fish outline when sensor is operating with CPU(80C196KC). Then, after signal processing, this feature is classified a special feature and a outline of fish by using the neural network, one of the artificial intelligence scheme. This neural network classifies fish pattern of very simple and short calculation. This has linear activation function and the error back propagation is used as a teaming algorithm. And the neural network is learned in off-line process. Because an adaptation period of neural network is too long when random initial weights are used, off-line teaming is induced to decrease the progress time.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.12
• /
• pp.2622-2627
• /
• 2010

The accuracy of face recognition used unmanned security system is very important and necessary. However, face recognition is a lot of restriction due to the change of distortion of face image, illumination, face size, face expression, round image. We propose a hybrid neural network for improve the performance of the face recognition. The proposed method is consisted of SOM and LVQ. In order to verify usefulness of the proposed method, we make a comparison between eigenface method, hidden Markov model method, multi-layer neural network.